© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 13579
    Prev
    Next
    INDEX
    Explanations

    indicators and causes for outcomes

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron detects methodological or measurement terms—nouns that label study metrics, indicators, predictors, sources of data, risk factors, etc.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    哟
    -1.04
    体型
    -1.02
    。。。。
    -1.01
    ！！！！！
    -1.01
    ☆☆☆☆
    -0.98
    〰
    -0.94
    ⼿
    -0.93
    名单
    -0.93
    -0.92
    ！！！！
    -0.91
    POSITIVE LOGITS
     determines
    0.99
     determine
    0.96
     to
    0.92
     rather
    0.90
     the
    0.90
     zamiast
    0.88
    več
    0.88
     determin
    0.86
     Themen
    0.86
    にならない
    0.84
    Activations Density 0.099%

    No Known Activations